Forums - Machine Vision Project Implementation

4 posts / 0 new
Last post
Machine Vision Project Implementation
Amine.RH
Join Date: 25 Apr 18
Posts: 10
Posted: Wed, 2018-04-25 05:57

Hello

I am an image-processing engineer,I work at MASciR,

We have developed an image processing application allowing the collection of traffic data by using camera. The application that we have based on c++ on an intel platform with a linux operating system, we use the Qt framework and OpenCV and to connect with the camera we used GigE Vision.

Now we are looking for the possibility of implementing on a snapdragon architecture.

Generally, how easy is it to make such an implementation?

Can we use QT?

Can we use OpenCV?

Can we use Genicam?

If so, what is the tutorial?

  • Up0
  • Down0
gmcgrath
Join Date: 21 Aug 13
Posts: 65
Posted: Thu, 2018-04-26 09:37

The Machine Vision SDK is very easy to use.  Platform questions should be directed to the appropriate platform.

  • Up0
  • Down0
Amine.RH
Join Date: 25 Apr 18
Posts: 10
Posted: Thu, 2018-04-26 12:43

tank you for your answer

that it is possible to implement a piece of code on GPU and the other part on CPU and the last part on DSP (the parallelism)?

 

 

 

Cheers,

Amine

 

  • Up0
  • Down0
gmcgrath
Join Date: 21 Aug 13
Posts: 65
Posted: Mon, 2018-04-30 08:58

Yes.  If you run mvDFS in GPU mode it will run on GPU while you can also run mvVISLAM on CPUin parallel which running the Snapdragon Navigator in parallel which runs on the DSP.

  • Up0
  • Down0
or Register

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.